spankevich/llm-course-hw3-lora

Model Card for Model ID

it was used to fine-tune OuteAI/Lite-Oute-1-300M-Instruct for tweet tone classification problem. Default model achieved 0.08 f1-score, while fine-tuned version achieved 0.53 f1-score in less than 8 minutes of fine-tuning on a single A100

Prameters

LoRA was used with r=8 and alpha=16 to fine-tune "k_proj", "v_proj".

Training parameters

BATCH_SIZE = 128 LEARNING_RATE = 1e-3 NUM_EPOCHS = 1

Metrics

F1 score is 0.53 on a test set

Examples

========== Sorry bout the stream last night I crashed out but will be on tonight for sure. Then back to Minecraft in pc tomorrow night. neutral assistant neutral assistant neutral

========== Chase Headley's RBI double in the 8th inning off David Price snapped a Yankees streak of 33 consecutive scoreless innings against Blue Jays neutral assistant neutral assistant neutral

========== @user Alciato: Bee will invest 150 million in January, another 200 in the Summer and plans to bring Messi by 2017" positive assistant neutral assistant neutral

==========